AI Tools
140 prompts in this category · Page 10 of 12
Ollama Modelfile from a Role Brief (No Invented Model Tags)
Write an Ollama Modelfile (FROM, SYSTEM, PARAMETER) from a role brief. If base model tag is UNKNOWN, write FROM UNKNOWN and do not invent llama3.1:70b. Not Custom GPT, Gemini Gem, Claude Project, or Cursor rules.
Act as an Ollama Modelfile author who only uses a pasted role brief. You write FROM, SYSTEM, and PARAMETER lines. You do not invent base model tags. This is not Custom GPT instructions, not a Gemini Gem, not a Claude Project, and not Cursor rules. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Role brief (behavior, refusals, tone): [Brief] - Base model tag (or UNKNOWN): [Tag] - Parameters I allow (temperature, num_ctx, etc. or NONE): [Params] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - SYSTEM length max (chars): [SMax or 2000] - Adapter / LoRA path (or NONE): [Adapter] Generate: 1. Honesty ledger: Brief nouns, Tag, Params, Adapter, SMax, Lang. 2. FROM line: exact Tag or FROM UNKNOWN (never invent llama3.1:70b). 3. SYSTEM block from Brief under SMax; print char count. 4. PARAMETER lines only from Params or PARAMETER NONE. 5. Adapter: if NONE write ADAPTER NONE. 6. Sample ollama create command using Tag or UNKNOWN note. 7. Refuse: inventing model tags, Custom GPT blocks, Gemini Gem, Claude Project, Cursor rules. 8. Compliance pass: Banned and Never. Format as Format. Gaps list of five. Constraints: - Ollama Modelfile from Brief only. No invented model tags. - If Tag UNKNOWN write FROM UNKNOWN. - Not Custom GPT / Gem / Claude Project / Cursor rules. - No emojis.
Semantic Kernel Plugin Skill Brief from a Tools List
Draft a Semantic Kernel plugin/skill brief from a tools list. No invented APIs, endpoints, or package versions.
Act as a Semantic Kernel plugin brief writer who only uses a pasted tools list. You draft plugin/skill names, descriptions, and parameter tables. You do not invent REST endpoints, SDK methods, or package versions. This is not a LangChain clone and not an AutoGen roster. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Tools list (name, purpose, params allowed): [Tools] - SK version I allow (or UNKNOWN): [Version] - Language/runtime I allow: [Runtime] - Plugin name I allow: [Plugin] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Tools nouns, Version, Runtime, Plugin, Lang. 2. Version lock: print Version or VERSION UNKNOWN. 3. Plugin overview: Plugin name + one-liner purpose from Tools only. 4. Skill table: one row per tool in Tools with name, description, params (only params listed). 5. Missing params: for any tool without params, write PARAMS NOT IN TOOLS LIST. 6. Auth/config: only if Tools names secrets/config keys; else AUTH/CONFIG NOT IN TOOLS LIST. 7. Refuse: inventing HTTP paths, inventing NuGet/PyPI versions, inventing SK connectors not listed. 8. Compliance pass: Banned and Never. Format as Format. Constraints: - Semantic Kernel brief from Tools list only. No invented APIs. - Never invent endpoints, SDK methods, or package versions. - Keep Version UNKNOWN when blank. - No emojis.
AutoGen Agent Roster from a Multi-Agent Brief
Draft an AutoGen-style agent roster, roles, and handoffs from a multi-agent brief. Never invent tools or model names not locked.
Act as an AutoGen roster clerk who only uses a pasted multi-agent brief. You list agents, system roles, allowed tools, and handoff rules. You do not invent tools or model IDs. This is not a LangGraph card, not a CrewAI YAML card, and not a full app scaffold. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Multi-agent brief: [Brief] - Agent count max: [N or 4] - Tool allowlist: [Tools] - Model I lock (or UNKNOWN): [Model] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Brief nouns, N, Tools, Model, Lang. 2. Model lock: Model or MODEL UNKNOWN. 3. Up to N agents: name, role summary from Brief, tools subset of Tools only. 4. Handoff table: from-agent -> to-agent with trigger quoted from Brief or TRIGGER UNKNOWN. 5. Shared memory note: only if Brief states it; else SHARED MEMORY NOT IN INPUTS. 6. Refuse: inventing tools outside Tools, inventing OpenAI model IDs, inventing AutoGen API versions. 7. Termination condition: only if Brief states it; else TERMINATION NOT IN INPUTS. 8. Compliance pass: Banned and Never. Format as Format. Constraints: - AutoGen roster from Brief+Tools only. Not LangGraph/CrewAI. - Never invent tools or model IDs. - Keep Model UNKNOWN when blank. - No emojis.
LangGraph StateGraph Nodes Edges and Reducers from an Agent Brief (No Invented Tools)
Sketch a LangGraph StateGraph with nodes, edges, and reducers from an agent brief. Do not invent tools or node names not listed.
Act as a LangGraph StateGraph sketcher who only uses a pasted agent brief. You list state keys, nodes, edges, and reducers. You do not invent tools, model IDs, or extra nodes. This is not a LangGraph node-only sketch from a workflow brief, not LangChain LCEL dump, and not a CrewAI yaml. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Agent brief (goal, steps, tools allowed): [Brief] - LangGraph version I lock (or UNKNOWN): [Version] - Tools I allow (or NONE): [Tools] - State keys I allow (or UNKNOWN): [State] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Model I lock (or UNKNOWN): [Model] Generate: 1. Honesty ledger: Brief nouns, Version, Tools, State, Model, Lang. Forbidden: extra tools, extra nodes, inventing checkpointers. 2. Version line: quote Version or VERSION UNKNOWN. 3. State: keys only from State or derive names from Brief nouns and mark DERIVED FROM BRIEF; if State UNKNOWN and Brief lacks nouns, write STATE UNKNOWN. 4. Nodes: one per step in Brief. No extra nodes. 5. Edges: linear unless Brief names a branch. Conditional edge only if Brief has a branch word. 6. Reducers: only if State says a key is a list/merge; else REDUCER NOT IN INPUTS. 7. Refuse: inventing Tavily, inventing a memory saver, inventing gpt-5 if Model UNKNOWN, LCEL dump. 8. Compliance pass: Banned and Never. Format as Format. Constraints: - LangGraph StateGraph from an agent brief. Not a workflow-brief node-only card. - Never invent tools, extra nodes, or model IDs. - No emojis.
OpenAI Assistants API System Instructions from a Tools Brief (No Invented Tools)
Write Assistants API system instructions from a tools brief. Do not invent tools, function names, or model IDs not locked in Inputs.
Act as an OpenAI Assistants API system-instructions writer who only uses a pasted tools brief. You write Role, Goal, Input, Output, Constraints, and a tools allowlist. You do not invent function names, vector-store IDs, or model IDs. This is not a Custom GPT store listing, not a ChatGPT Projects pack, and not a Cursor rules file. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Tools brief (who it helps, allowed tools, what a good answer looks like): [Brief] - Model I lock (or UNKNOWN): [Model] - Tools I allow (file_search / code_interpreter / function names as pasted / NONE): [Tools] - Function signatures I allow (or NONE): [Functions] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Product I lock: [Product or OpenAI Assistants API] Generate: 1. Honesty ledger: Brief nouns, Model, Tools, Functions, Product, Lang. Forbidden: extra tools, inventing gpt-5 if UNKNOWN, inventing function names. 2. Role block: one paragraph from Brief. Product quoted. 3. Goal block: quote the goal in Brief. Do not add extra success metrics. 4. Tools allowlist: only Tools. If a tool is missing, write NOT IN INPUTS. Function names only from Functions. 5. Input/Output blocks from Brief only. 6. Constraints: copy hard lines from Brief. Model quoted or MODEL UNKNOWN. 7. Refuse: Custom GPT OpenAPI invent, Cursor .mdc, ChatGPT Projects starters, invented vector-store IDs. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - OpenAI Assistants API system instructions from Brief. Not a Custom GPT listing and not Cursor rules. - Only Tools and Functions named in Inputs. - Never invent model IDs or extra tools. - No emojis.
Cursor Rules .mdc from a Repo Brief (No Invented Tools)
Write Cursor rules in .mdc style from a repo brief. Do not invent tools, paths, or package managers not listed.
Act as a Cursor rules .mdc custom-instructions builder who only uses a pasted role brief. You write five blocks: Role, Goal, Input, Output, Constraints. You do not write a rulesini rules YAML, a ChatGPT Projects pack, or a Custom GPT store listing. You do not invent tools, files, or API keys. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Role brief (who it helps, what a good answer looks like): [Brief] - Goal I lock: [Goal] - Input types I allow: [InputTypes] - Output shape I allow: [Output] - Constraints I lock: [ConstraintsIn] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Product I lock: [Product or Cursor rules .mdc] Generate: 1. Honesty ledger: Brief nouns, Goal, InputTypes, Output, ConstraintsIn, Product, Lang. Forbidden: rulesini rules, ChatGPT Projects, API keys, extra tools. 2. Role block: one paragraph from Brief. Product quoted. 3. Goal block: quote Goal. Do not add extra success metrics. 4. Input block: only InputTypes. If a file type is missing, write NOT IN INPUTS. 5. Output block: quote Output. Do not invent a JSON schema the brief lacks. 6. Constraints: copy ConstraintsIn. Do not add extra nevers unless Brief names them. 7. Refuse: rulesini rules YAML, ChatGPT Projects starters invent, Custom GPT OpenAPI. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Cursor rules .mdc instructions from Brief. Not a rulesini rules and not a ChatGPT Project. - Only InputTypes named in Inputs. - Never invent API keys or extra tools. - No emojis. Also lock globs and alwaysApply from Inputs. Package manager UNKNOWN means PM UNKNOWN.
Mistral Le Chat Custom Instructions (Role, Goal, Input, Output, Constraints)
Build Mistral Le Chat custom instructions from a role brief: role, goal, input, output, constraints. Not a Gemini Gem and not a ChatGPT Project.
Act as a Mistral Le Chat custom-instructions builder who only uses a pasted role brief. You write five blocks: Role, Goal, Input, Output, Constraints. You do not write a Gemini Gem YAML, a ChatGPT Projects pack, or a Custom GPT store listing. You do not invent tools, files, or API keys. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Role brief (who it helps, what a good answer looks like): [Brief] - Goal I lock: [Goal] - Input types I allow: [InputTypes] - Output shape I allow: [Output] - Constraints I lock: [ConstraintsIn] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Product I lock: [Product or Mistral Le Chat] Generate: 1. Honesty ledger: Brief nouns, Goal, InputTypes, Output, ConstraintsIn, Product, Lang. Forbidden: Gemini Gem, ChatGPT Projects, API keys, extra tools. 2. Role block: one paragraph from Brief. Product quoted. 3. Goal block: quote Goal. Do not add extra success metrics. 4. Input block: only InputTypes. If a file type is missing, write NOT IN INPUTS. 5. Output block: quote Output. Do not invent a JSON schema the brief lacks. 6. Constraints: copy ConstraintsIn. Do not add extra nevers unless Brief names them. 7. Refuse: Gemini Gem YAML, ChatGPT Projects starters invent, Custom GPT OpenAPI. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Mistral Le Chat instructions from Brief. Not a Gemini Gem and not a ChatGPT Project. - Only InputTypes named in Inputs. - Never invent API keys or extra tools. - No emojis.
ChatGPT Projects Instructions Builder from a Role Brief (Never-List, Escalation, Starters)
Build ChatGPT Projects custom instructions from a role brief: role, never-list, escalation, starters. Not a Custom GPT store listing.
Act as a ChatGPT Projects instructions builder who only uses a pasted role brief. You write Project instructions with a role, a never-list, an escalation rule, and conversation starters. You do not write a Custom GPT public store listing, a Gemini Gem, or an OpenWebUI pack. You do not invent tools, files, or API keys. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Role brief (who it helps, what a good answer looks like): [Brief] - Never-list I lock: [NeverList] - Escalation I allow (when to stop and ask a human): [Escalation] - Starters I allow (or NONE): [Starters] - Files I may mention (or NONE): [Files] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Product I lock: [Product or ChatGPT Projects] Generate: 1. Honesty ledger: Brief nouns, NeverList, Escalation, Starters, Files, Product, Lang. Forbidden: Custom GPT store name, Gemini Gem, API keys, extra files. 2. Role block: one paragraph from Brief. Product quoted. 3. Never-list: copy NeverList. Do not add extra nevers unless Brief names them. 4. Escalation: quote Escalation. If blank, write ESCALATION NOT IN INPUTS rather than inventing a phone tree. 5. Starters: only Starters. If NONE, write three blanks labeled STARTER NOT IN INPUTS rather than inventing cute prompts. 6. Files: only Files. If NONE, do not invent a knowledge PDF. 7. Refuse: Custom GPT configure-tab dump, Action OpenAPI, Gemini Gem YAML. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - ChatGPT Projects instructions from Brief. Not a Custom GPT store listing and not a Gemini Gem. - Only Files and Starters named in Inputs. - Never invent API keys or extra tools. - No emojis.
CrewAI Role and Task YAML from a Multi-Agent Brief
Write CrewAI role and task YAML from a multi-agent brief. No invented package versions, tools, or API keys.
Act as a CrewAI YAML sketcher who only uses a pasted multi-agent brief. You write role and task YAML for CrewAI from the brief. You do not invent package versions, API keys, tools not listed, or agents not named. This is not a LangGraph node sketch and not a runnable deploy. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Multi-agent brief: [Brief] - CrewAI version I lock (or UNKNOWN): [Version] - Agent names and goals I allow: [Agents] - Tools I may name: [Tools] - Process type I allow (sequential/hierarchical or UNKNOWN): [Process] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language for backstory stubs: [Lang] - Human review points: [HITL] Generate: 1. Honesty ledger: Brief, Version, Agents, Tools, Process, HITL, Lang. Forbidden: keys, extra agents, extra tools, versions not locked. 2. Role YAML: one agent block per Agents entry. Role, goal, backstory from Brief only. No model SKU if not in Brief. 3. Task YAML: one task per job in Brief. description, expected_output, agent from Agents. No secret values. 4. Process: only Process. If UNKNOWN, write process: UNKNOWN and do not pick hierarchical by default. 5. Tools: attach only Tools named. If a task needs a tool not listed, write NOT IN INPUTS rather than adding one. 6. HITL: insert a human review note only at HITL points. 7. Refuse: inventing OpenAI model names, Redis memory URLs, or API keys. 8. Compliance pass: cut Banned and Never. Print that Version is quoted or UNKNOWN. Format as Format. Constraints: - CrewAI role and task YAML from Brief. Not a LangGraph sketch and not a production deploy. - Never invent API keys or package versions when Version is UNKNOWN. - Only Tools and Agents named in Inputs. - No emojis.
OpenWebUI System Prompt Pack from a Role Library
Build OpenWebUI system prompt packs from a role library you paste. No invented model SKUs or admin credentials.
Act as an OpenWebUI admin writing system prompt packs from a role library. You turn a role library into OpenWebUI system prompts and brief starter messages. You do not invent model SKUs, API bases, or admin credentials. This is not a bypass pack and not a Modelfile for Ollama unless asked. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Role library entries: [Roles] - OpenWebUI version I lock (or UNKNOWN): [Version] - Safety rules I require in every pack: [Safety] - Tools each role may call (or NONE): [Tools] - Words I must not use: [Banned] - What I must never invent: [Never] - Tone defaults: [Tone] - Output format: [Format] - Max system prompt words: [Max] - Starter user messages needed: [Starters] Generate: 1. Honesty ledger: Roles, Version, Safety, Tools, Tone, Max, Starters. Forbidden: SKUs, admin credentials, bypass packs. 2. One pack per Roles entry: title, system prompt, starter. 3. Inject Safety lines into every system prompt. 4. Tools allow list only if not NONE. 5. Word count under Max; print counts. 6. Refuse: bypass packs and credential exfil requests. 7. Version note: UNKNOWN vs locked. 8. Compliance pass: cut Banned and Never. Format as Format. Constraints: - OpenWebUI system prompt packs from Roles. Not bypass packs. - Never invent model SKUs or admin credentials. - Honor Max word budget with counts. - Include Safety in every pack. - No emojis.
LangGraph Node Sketch from a Workflow Brief
Sketch LangGraph nodes and edges from a workflow brief. No invented package versions or API keys.
Act as a LangGraph workflow sketcher who only uses a pasted workflow brief. You sketch nodes, edges, and state fields for LangGraph from a workflow brief. You do not invent package versions, API keys, or tools not listed. This is not a full runnable app and not a LangChain agent dump unrelated to the brief. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Workflow brief: [Brief] - LangGraph version I lock (or UNKNOWN): [Version] - State fields I allow: [State] - Tools or retrievers I may name: [Tools] - Human-in-the-loop points: [HITL] - Words I must not use: [Banned] - What I must never invent: [Never] - Failure modes I care about: [Fails] - Output format: [Format] - Language for stubs (Python/TS): [Lang] Generate: 1. Honesty ledger: Brief, Version, State, Tools, HITL, Fails, Lang. Forbidden: keys, versions not locked, extra tools. 2. Node list with one-line purpose each from Brief. 3. Edge list including conditional edges only if Brief states a branch. 4. State schema using State fields only. 5. HITL breakpoints only as listed. 6. Stub signatures in Lang without real credential values. 7. Refuse: inventing model names not in Brief. 8. Compliance pass: cut Banned and Never. Format as Format. Constraints: - LangGraph sketch from Brief. Not a production deploy guide. - Never invent API keys or package versions when Version is UNKNOWN. - Only Tools named in Inputs. - No emojis.
Aider Conventions File from a Repo Brief (No AGENTS.md Duplicate)
Write Aider CONVENTIONS.md and .aider.conf.yml from a repo brief. No AGENTS.md, no invented models.
Act as an Aider power user writing CONVENTIONS.md and .aider.conf.yml from a repo brief. You write Aider conventions from a stack brief. Lock model names to Inputs. Thin Cursor mdc only if asked. Never emit AGENTS.md, Continue, Copilot, Cline, or Windsurf files. Focus Aider: architect vs code, read, lint, ignore globs. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Aider version I use: [Version] - Repo languages, test command, lint command: [Stack] - Models I may call (provider plus model id): [Models] - Architect vs code preference: [Mode] - Files Aider must --read every session: [Read] - Ignore globs: [Ignore] - Whether to also emit a thin Cursor mdc (yes/no): [CursorSplit] - Words I must not use: [Banned] - Auth env var name only: [Auth] - What other assistant files I must not write: [NotFiles] Generate: 1. Honesty ledger: version, languages, test and lint, model ids, read files, ignore. Forbidden: models not in Models, files in NotFiles, AGENTS.md. 2. CONVENTIONS.md: never-list, test and lint from Stack, read files from Read, architect vs code from Mode. 3. aider conf yml: model from Models only, lint-cmd, test-cmd, read, ignore. Version comment. 4. Cursor split: if CursorSplit is yes, one short cursor rules file pointing at CONVENTIONS.md. If no, omit. 5. Refuse: list NotFiles including AGENTS.md you will not emit. 6. Auth: print only the env var name. Do not print a token. 7. Run notes: aider locked to Version. Watch only if Inputs asked. 8. Compliance pass: quote Banned words, invented model ids, AGENTS.md body. Cut them. Constraints: - Aider CONVENTIONS.md and aider conf yml. Do not write AGENTS.md, Continue, Copilot, Cline, or Windsurf files. - Never invent a model id. - Cursor mdc only if CursorSplit is yes, and it must not duplicate AGENTS.md. - Test and lint commands only from Stack. - No emojis.